Environment active sensing-type automatic parking system in parking lot

Abstract

Disclosed is an environment active sensing-type automatic parking system in a parking lot, including a vehicle information acquisition and identification module, a multi-sensor positioning module, a building information model module, a classification processing module, path planning and navigation module, a parking space state judgment module, a two-flywheel steering device and a mechanical power device. A QR code, a mechanical power device, and a two-flywheel steering device are mounted onto a vehicle, the QR code is identified by using a camera in the parking lot to achieve continuous positioning, an optimal path is planned according to vehicle distribution information in the current parking lot, and the driving speed and driving direction of the vehicle are controlled by remotely controlling the mechanical power device in the vehicle, so as to achieve automatic parking in the parking lot.

What is claimed is: 
     
         1 . An environment active sensing-type automatic parking system in a parking lot, wherein the system comprises a vehicle information acquisition and identification module, a multi-sensor positioning module, a building information model module, a classification processing module, a path planning and navigation module, a parking space state judgment module, a two-flywheel steering device, and a mechanical power device;
 the vehicle information acquisition and identification module comprises a number of cameras mounted in the parking lot and QR codes mounted onto rooves of vehicles; and the vehicle information acquisition and identification module acquires vehicle information, and a unique ID is assigned to each of the vehicles;   the multi-sensor positioning module receives the vehicle information acquired by the vehicle information acquisition and identification module, and positions the vehicles;   the building information model module is configured to establish a space model for building information of the parking lot, generate a GIS electronic map, and mark parking spaces and vehicle positions in the parking lot in the electronic map;   the parking space state judgment module is configured to judge whether there are vehicles in the parking spaces to obtain parking space state information;   the path planning and navigation module is configured to plan an optimal path according to vehicle distribution and the parking space state information in the lot, so as to navigate vehicles into the parking spaces;   the two-flywheel steering device is mounted at a maximum diameter of a steering wheel, a two-flywheel device comprises a gyro sensor, the moment of inertia of two flywheels and a speed difference between the two flywheels enable the steering wheel to rotate in a designated direction and at a designated angle, and a deflection angle of the steering wheel is calculated according to a height difference between the two flywheels, an angle between a plane where the steering wheel is located and a horizontal plane, and a diameter of the steering wheel;   the mechanical power device comprises a first motor and a second motor, the first motor is configured to control lifting up or pressing down an accelerator pedal, and the second motor is configured to control lifting up or pressing down a brake pedal;   the classification processing module classifies the acquired vehicle information into three categories, which are a manual driving vehicle, a semi-autonomous driving vehicle, and a full-autonomous driving vehicle respectively;   the manual driving vehicle comprises a QR code, a mechanical power device, and a two-flywheel steering device mounted onto the roof of the vehicle, and automatic parking of the manual driving vehicle is achieved by turning the steering wheel through the moment of inertia of the two flywheels and coordinated control of the two flywheels;   the semi-autonomous driving vehicle comprises an autonomous driving power device and a control device, and a QR code mounted onto the roof of the vehicle, so as to achieve communication of position information and environmental information between the parking lot and the vehicle, and an automatic parking function is achieved by using a semi-autonomous driving apparatus of the vehicle; and   the full-autonomous driving vehicle comprises complete power and control devices, and a sensor capable of identifying an environment, the parking lot establishes communication with the full-autonomous driving vehicle, and an automatic parking function is achieved by sending path planning, parking space state information, and vehicle distribution information to the vehicle.   
     
     
         2 . The environment active sensing-type automatic parking system in a parking lot according to  claim 1 , wherein the vehicle information acquired by the vehicle information acquisition and identification module comprises: vehicle entry time, license plate number, and other information, a unique ID is assigned to each of the vehicles according to the license plate number, and the cameras in the vehicle information acquisition and identification module are capable of acquiring and identifying information of the vehicle in every corner of the parking lot without dead angles. 
     
     
         3 . The environment active sensing-type automatic parking system in a parking lot according to  claim 1 , wherein in the vehicle information acquisition and identification module, a polarized light receiver is further mounted around the vehicle to replace the QR code on the roof of the vehicle. 
     
     
         4 . The environment active sensing-type automatic parking system in a parking lot according to  claim 1 , wherein the system further comprises WIFi, Bluetooth, and ZigBee communication devices for auxiliary positioning. 
     
     
         5 . The environment active sensing-type automatic parking system in a parking lot according to  claim 1 , wherein the multi-sensor positioning module is a binocular camera, and calculation formulas of a real coordinate value of a vehicle position are as follows: 
       
         
           
             
               d 
               = 
               
                  
                 
                   xl 
                   - 
                   xr 
                 
                  
               
             
           
         
         
           
             
               x 
               = 
               
                 
                   B 
                   · 
                   xl 
                 
                 d 
               
             
           
         
         
           
             
               y 
               = 
               
                 
                   
                     
                       B 
                       · 
                       yt 
                     
                     d 
                   
                   ⁢ 
                   
                     
 
                   
                   ⁢ 
                   z 
                 
                 = 
                 
                   
                     f 
                     · 
                     B 
                   
                   d 
                 
               
             
           
         
         wherein f is a camera focal length, coordinates of left and right cameras are (xl, yl) and (xr, yr) respectively, the two cameras have the same height, and thus yl=yr=yt, B is a baseline distance between the two cameras, and d is an absolute value of an x-axis difference between the left and right cameras. 
       
     
     
         6 . The environment active sensing-type automatic parking system in a parking lot according to  claim 1 , wherein the multi-sensor positioning module is a multi-view camera, the QR code on the vehicle is captured by multiple cameras, and a real coordinate value of the vehicle is obtained by making adjustment calculation by using a multi-sensor fusion method. 
     
     
         7 . The environment active sensing-type automatic parking system in a parking lot according to  claim 1 , wherein the path planning and navigation module calculates vehicle density on each route, and then calculates an optimal path of a to-be-parked vehicle in combination with a breadth first algorithm; generates a corresponding control algorithm according to optimal path information of each vehicle, and then sends a control instruction to the two-flywheel steering device and the mechanical power device in the vehicle through remote communication to navigate the vehicle. 
     
     
         8 . The environment active sensing-type automatic parking system in a parking lot according to  claim 1 , wherein the system further comprises a feedback self-correction module, which is configured to position a vehicle by identifying the QR code on the roof of the vehicle when the vehicle deviates from an originally planned path, calculate an error between the position and a correct position, and then correct the position and attitude of the vehicle through a PID feedback control algorithm. 
     
     
         9 . The environment active sensing-type automatic parking system in a parking lot according to  claim 1 , wherein the mechanical power device is configured to control movement and stop of the vehicle, and feed back vehicle speed and direction signals to a feedback self-correction module. 
     
     
         10 . The environment active sensing-type automatic parking system in a parking lot according to  claim 1 , wherein the gyro sensor in the two-flywheel steering device calculates a height difference h between the two flywheels, a projection of the height difference between the two flywheels onto the plane where the steering wheel is located is recorded as h′, the angle between the plane where the steering wheel is located and the horizontal plane is recorded as α, and the diameter of the steering wheel is recorded as L; then the deflection angle θ of the steering wheel is calculated based on the following calculation formulas: 
       
         
           
             
               
                 h 
                 ′ 
               
               = 
               
                 h 
                 ⁢ 
                 
                   / 
                 
                 ⁢ 
                 sin 
                 ⁢ 
                 
                     
                 
                 ⁢ 
                 α 
               
             
           
         
         
           
             
               θ 
               = 
               
                 arctan 
                 ⁢ 
                 
                   
                     
                       2 
                       ⁢ 
                       
                         h 
                         ′ 
                       
                     
                     L 
                   
                   .